biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Multimodal][Speculative Decoding]Eagle Eagle3 mm support, enablement on qwen2.5vl (#22872)

Browse Source 
Signed-off-by: Junhong <liujunhong11@huawei.com>
Signed-off-by: Junhong Liu <98734602+LJH-LBJ@users.noreply.github.com>
Co-authored-by: Junhong <liujunhong11@huawei.com>
Co-authored-by: LJH-LBJ <98734602+LJH-LBJ@users.noreply.github.com>
This commit is contained in:
WeiQing Chen
2025-09-27 11:35:47 +08:00
committed by GitHub
parent 92da847cf5
commit f1d53d150c
8 changed files with 210 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/model_executor/models/registry.py
View File

@@ -286,6 +286,7 @@ _SPECULATIVE_DECODING_MODELS = {
"EagleMiniCPMForCausalLM": ("minicpm_eagle", "EagleMiniCPMForCausalLM"),
"Eagle3LlamaForCausalLM": ("llama_eagle3", "Eagle3LlamaForCausalLM"),
"LlamaForCausalLMEagle3": ("llama_eagle3", "Eagle3LlamaForCausalLM"),
"Eagle3Qwen2_5vlForCausalLM": ("llama_eagle3", "Eagle3LlamaForCausalLM"),
"EagleDeepSeekMTPModel": ("deepseek_eagle", "EagleDeepseekV3ForCausalLM"),
"DeepSeekMTPModel": ("deepseek_mtp", "DeepSeekMTP"),
"ErnieMTPModel": ("ernie_mtp", "ErnieMTP"),